The Unreasonable Effectiveness of Deep Feature Extraction

Re:The Unreasonable Effectiveness of Deep Feature Extraction by bobosha on Thursday February 14, 2019 @02:23PM (#19164994)

This is very interesting and timely to my work, I had been struggling with training a Mobilenet CNN for classification of human emotions ("in the wild"), and struggling to get the model to converge. I tried multiclass to binary models e.g. angry|not_angry etc. But couldn't get past the 60-70% accuracy range.

I switched to extracting features from Imagenet and trained an xgboost binary and boom...right out of the box am seeing ~88% accuracy.

Also the author's points about speed of training and flexibility is major plus for my work. Hope this helps others.

[ Parent | on HN ]

Re:The Unreasonable Effectiveness of Deep Feature Extraction by mlucy on Thursday February 14, 2019 @02:40PM (#19165200)

Yeah, I think this pattern is pretty common. (Basilica's main business is an API that does deep feature extraction as a service, so we end up talking to a lot of people with tasks like yours -- and there are a lot of them.)

We're actually working on an image model specialized for human faces right now, since it's such a common problem and people usually don't have huge datasets.

[ Parent | on HN ]